It’s not that crazy, just the architecture of differently quantized models and s... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		BriggyDwiggs42 54 days ago \| parent \| context \| favorite \| on: We Can Just Measure Things It’s not that crazy, just the architecture of differently quantized models and so on that you’d need to do that is impressive considering.

layer8 53 days ago [–]

The models are the same, it's the surrounding processing like "thinking" iterations that are adjusted.

BriggyDwiggs42 53 days ago | [–]

That only works for LRMs no? Not traditional LLM inference.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact